I've been working on something in a similar class for about a year called llcat

It came out of a lack of their being an LLM-native tool that feels like cURL or other unix-friendly things such as awk or sed.

I was tired of claude generating nearly identical 50 line scripts every time I wanted to just talk to an endpoint.

I wanted something stateless, explicit, low-level, and composable without settings like grep, ps, mount, sort.

Instead, you can index into files with jq or line numbers and save invocations for later for instance

    llcat --save invocation.json \
      -k "@~/credentials.txt:12" \
      -u "@settings.json:.[3].host" \
      -s "@system_prompts:8" \
      -m "@settings.json:.[3].model" \
         "@query.txt:12" > output.txt

and then

   llcat --load invocation.json { ... parameters you want to override ... }

Conversations are stored as JSON files and you can have a different one input and output. This means you can do stuff like

   for i in *; do 
     cat "$i" | llcat --load settings.json -cr context.json  > ../results/"${i}.output"
   done

And use a non-mutable conversation to apply the same context over a group of files.

Since there's no hidden state you can use it in shell scripts and get operational guarantees.

For instance, I have this line in a separate project

    sc_pane="${pane_list[0]}" llcat "$dry" \
      -c "$convo_id" \
      "${tool[@]}" --timeout "$TIMEOUT" \
      -m "$LLM_MODEL" -bq result \
      -u "$SERVER_URL" "${system[@]}" \
      "${key[@]}" "$@" 2> >(cat >&2)

I've put a lot of effort into this and use it daily. I really wish people would give it a go and give me feedback and file bugs!

https://github.com/day50-dev/llcat

OpenAI CLI